Sleep apnea phenotyping and relationship to disease in a large clinical biobank

Age modulates the predictive value of self-reported sleepiness for all-cause mortality risk: insights from a comprehensive national database of veterans

STUDY OBJECTIVES

Excessive daytime sleepiness is prevalent and overwhelmingly stems from disturbed sleep. We hypothesized that age modulates the association between excessive daytime sleepiness and increased all-cause mortality.

METHODS

We utilized the Veterans' Health Administration data from 1999-2022. We enrolled participants with sleep related International Classification of Diseases 9/10 codes or sleep services. A natural language processing pipeline was developed and validated to extract the Epworth Sleepiness Scale (ESS) as a self-reported tool to measure excessive daytime sleepiness from physician progress notes. The natural language processing's accuracy was assessed through manual annotation of 470 notes. Participants were categorized into normal-ESS (ESS 0-10) and high-ESS (ESS 11-24). We created 3 age groups: < 50 years, 50 to < 65 years, and ≥ 65 years. The adjusted odds ratio of mortality was calculated for age, body mass index, sex, race, ethnicity, and the Charlson Comorbidity Index, using normal-ESS as the reference. Subsequently, we conducted age stratified analysis.

RESULTS

The first ESS records were extracted from 423,087 veterans with a mean age of 54.8 (± 14.6), mean body mass index of 32.6 (± 6.2), and 90.5% male. The adjusted odds ratio across all ages was 17% higher (1.15, 1.19) in the high-ESS category. The adjusted odds ratio s only became statistically significant for individuals aged ≥ 50 years in the high-ESS compared to the normal-ESS category (< 50 years: 1.02 [0.96, 1.08], 50 to < 65 years 1.13[1.10, 1.16]; ≥ 65 years: 1.25 [1.21, 1.28]).

CONCLUSIONS

High-ESS predicted increased mortality only in participants aged 50 and older. Further research is required to identify this differential behavior in relation to age.

CITATION

Maghsoudi A, Azarian M, Sharafkhaneh A, et al. Age modulates the predictive value of self-reported sleepiness for all-cause mortality risk: insights from a comprehensive national database of veterans. J Clin Sleep Med. 2024;20(11):1785-1792.

Scalable incident detection via natural language processing and probabilistic language models

Post marketing safety surveillance depends in part on the ability to detect concerning clinical events at scale. Spontaneous reporting might be an effective component of safety surveillance, but it requires awareness and understanding among healthcare professionals to achieve its potential. Reliance on readily available structured data such as diagnostic codes risks under-coding and imprecision. Clinical textual data might bridge these gaps, and natural language processing (NLP) has been shown to aid in scalable phenotyping across healthcare records in multiple clinical domains. In this study, we developed and validated a novel incident phenotyping approach using unstructured clinical textual data agnostic to Electronic Health Record (EHR) and note type. It's based on a published, validated approach (PheRe) used to ascertain social determinants of health and suicidality across entire healthcare records. To demonstrate generalizability, we validated this approach on two separate phenotypes that share common challenges with respect to accurate ascertainment: (1) suicide attempt; (2) sleep-related behaviors. With samples of 89,428 records and 35,863 records for suicide attempt and sleep-related behaviors, respectively, we conducted silver standard (diagnostic coding) and gold standard (manual chart review) validation. We showed Area Under the Precision-Recall Curve of ~ 0.77 (95% CI 0.75-0.78) for suicide attempt and AUPR ~ 0.31 (95% CI 0.28-0.34) for sleep-related behaviors. We also evaluated performance by coded race and demonstrated differences in performance by race differed across phenotypes. Scalable phenotyping models, like most healthcare AI, require algorithmovigilance and debiasing prior to implementation.

Identifying clusters of patient comorbidities associated with obstructive sleep apnea using electronic health records

STUDY OBJECTIVES

The objectives of this study were to understand the relative comorbidity burden of obstructive sleep apnea (OSA), determine whether these relationships were modified by sex or age, and identify patient subtypes defined by common comorbidities.

METHODS

Cases with OSA and noncases (controls) were defined using a validated electronic health record (EHR)-based phenotype and matched for age, sex, and time period of follow-up in the EHR. We compared prevalence of the 20 most common comorbidities between matched cases and controls using conditional logistic regression with and without controlling for body mass index. Latent class analysis was used to identify subtypes of OSA cases defined by combinations of these comorbidities.

RESULTS

In total, 60,586 OSA cases were matched to 60,586 controls (from 1,226,755 total controls). Patients with OSA were more likely to have each of the 20 most common comorbidities compared with controls, with odds ratios ranging from 3.1 to 30.8 in the full matched set and 1.3 to 10.2 after body mass index adjustment. Associations between OSA and these comorbidities were generally stronger in females and patients with younger age at diagnosis. We identified 5 distinct subgroups based on EHR-defined comorbidities: High Comorbidity Burden, Low Comorbidity Burden, Cardiovascular Comorbidities, Inflammatory Conditions and Less Obesity, and Inflammatory Conditions and Obesity.

CONCLUSIONS

Our study demonstrates the power of leveraging the EHR to understand the relative health burden of OSA, as well as heterogeneity in these relationships based on age and sex. In addition to enrichment for comorbidities, we identified 5 novel OSA subtypes defined by combinations of comorbidities in the EHR, which may be informative for understanding disease outcomes and improving prevention and clinical care. Overall, this study adds more evidence that OSA is heterogeneous and requires personalized management.

CITATION

Te TT, Keenan BT, Veatch OJ, Boland MR, Hubbard RA, Pack AI. Identifying clusters of patient comorbidities associated with obstructive sleep apnea using electronic health records. J Clin Sleep Med. 2024;20(4):521-533.

Heritability and genetic correlations for sleep apnea, insomnia, and hypersomnia in a large clinical biobank

RATIONALE

Comorbid insomnia and sleep apnea is reported to have worse outcomes than either condition alone. The local genetic correlations of these disorders are unknown.

OBJECTIVES

To identify local genomic regions with heritability for clinically diagnosed sleep apnea and insomnia, and to identify local genetic correlations between these disorders and/or hypersomnia.

METHODS

Fifty thousand two hundred seventeen patients of European ancestry were examined. Global and local heritability and genetic correlations for independent regions were calculated, adjusting for obesity and other covariates.

RESULTS

Sleep apnea and insomnia were significantly globally heritable and had 118 and 168 genetic regions with local heritability p-values <.05, respectively. One region had a significant genetic correlation for sleep apnea and hypersomnia (p-value = 9.85 × 10-4).

CONCLUSIONS

Clinically diagnosed sleep apnea and insomnia have minimal shared genetic architecture, supporting genetically distinct comorbid insomnia and sleep apnea components. However, additional correlated regions may be identified with additional sample size and methodological improvements.

Scalable Incident Detection via Natural Language Processing and Probabilistic Language Models

Post marketing safety surveillance depends in part on the ability to detect concerning clinical events at scale. Spontaneous reporting might be an effective component of safety surveillance, but it requires awareness and understanding among healthcare professionals to achieve its potential. Reliance on readily available structured data such as diagnostic codes risk under-coding and imprecision. Clinical textual data might bridge these gaps, and natural language processing (NLP) has been shown to aid in scalable phenotyping across healthcare records in multiple clinical domains. In this study, we developed and validated a novel incident phenotyping approach using unstructured clinical textual data agnostic to Electronic Health Record (EHR) and note type. It's based on a published, validated approach (PheRe) used to ascertain social determinants of health and suicidality across entire healthcare records. To demonstrate generalizability, we validated this approach on two separate phenotypes that share common challenges with respect to accurate ascertainment: 1) suicide attempt; 2) sleep-related behaviors. With samples of 89,428 records and 35,863 records for suicide attempt and sleep-related behaviors, respectively, we conducted silver standard (diagnostic coding) and gold standard (manual chart review) validation. We showed Area Under the Precision-Recall Curve of ∼ 0.77 (95% CI 0.75-0.78) for suicide attempt and AUPR ∼ 0.31 (95% CI 0.28-0.34) for sleep-related behaviors. We also evaluated performance by coded race and demonstrated differences in performance by race were dissimilar across phenotypes and require algorithmovigilance and debiasing prior to implementation.

Strategies to Assess the Effect of Continuous Positive Airway Pressure on Long-Term Clinically Important Outcomes among Patients with Symptomatic Obstructive Sleep Apnea: An Official American Thoracic Society Workshop Report

Continuous positive airway pressure (CPAP) is the first-line treatment for obstructive sleep apnea (OSA). Although CPAP improves symptoms (e.g., daytime sleepiness), there is a lack of high-quality evidence that CPAP prevents many long-term outcomes, including cognitive impairment, myocardial infarction, and stroke. Observational studies suggest that patients with symptoms may be particularly likely to experience these preventive benefits with CPAP, but ethical and practical concerns limited the participation of such patients in prior long-term randomized trials. As a result, there is uncertainty about the full benefits of CPAP, and resolving this uncertainty is a key priority for the field. This workshop assembled clinicians, researchers, ethicists, and patients to identify strategies to understand the causal effects of CPAP on long-term clinically important outcomes among patients with symptomatic OSA. Quasi-experimental designs can provide valuable information and are less time and resource intensive than trials. Under specific conditions and assumptions, quasi-experimental studies may be able to provide causal estimates of CPAP's effectiveness from generalizable observational cohorts. However, randomized trials represent the most reliable approach to understanding the causal effects of CPAP among patients with symptoms. Randomized trials of CPAP can ethically include patients with symptomatic OSA, as long as there is outcome-specific equipoise, adequate informed consent, and a plan to maximize safety while minimizing harm (e.g., monitoring for pathologic sleepiness). Furthermore, multiple strategies exist to ensure the generalizability and practicality of future randomized trials of CPAP. These strategies include reducing the burden of trial procedures, improving patient-centeredness, and engaging historically excluded and underserved populations.

Discovery of genomic loci associated with sleep apnea risk through multi-trait GWAS analysis with snoring

STUDY OBJECTIVES

Despite its association with severe health conditions, the etiology of sleep apnea (SA) remains understudied. This study sought to identify genetic variants robustly associated with SA risk.

METHODS

We performed a genome-wide association study (GWAS) meta-analysis of SA across five cohorts (NTotal = 523 366), followed by a multi-trait analysis of GWAS (multi-trait analysis of genome-wide association summary statistics [MTAG]) to boost power, leveraging the high genetic correlation between SA and snoring. We then adjusted our results for the genetic effects of body mass index (BMI) using multi-trait-based conditional and joint analysis (mtCOJO) and sought replication of lead hits in a large cohort of participants from 23andMe, Inc (NTotal = 1 477 352; Ncases = 175 522). We also explored genetic correlations with other complex traits and performed a phenome-wide screen for causally associated phenotypes using the latent causal variable method.

RESULTS

Our SA meta-analysis identified five independent variants with evidence of association beyond genome-wide significance. After adjustment for BMI, only one genome-wide significant variant was identified. MTAG analyses uncovered 49 significant independent loci associated with SA risk. Twenty-nine variants were replicated in the 23andMe GWAS adjusting for BMI. We observed genetic correlations with several complex traits, including multisite chronic pain, diabetes, eye disorders, high blood pressure, osteoarthritis, chronic obstructive pulmonary disease, and BMI-associated conditions.

CONCLUSION

Our study uncovered multiple genetic loci associated with SA risk, thus increasing our understanding of the etiology of this condition and its relationship with other complex traits.

Machine learning approaches for electronic health records phenotyping: a methodical review

OBJECTIVE

Accurate and rapid phenotyping is a prerequisite to leveraging electronic health records for biomedical research. While early phenotyping relied on rule-based algorithms curated by experts, machine learning (ML) approaches have emerged as an alternative to improve scalability across phenotypes and healthcare settings. This study evaluates ML-based phenotyping with respect to (1) the data sources used, (2) the phenotypes considered, (3) the methods applied, and (4) the reporting and evaluation methods used.

MATERIALS AND METHODS

We searched PubMed and Web of Science for articles published between 2018 and 2022. After screening 850 articles, we recorded 37 variables on 100 studies.

RESULTS

Most studies utilized data from a single institution and included information in clinical notes. Although chronic conditions were most commonly considered, ML also enabled the characterization of nuanced phenotypes such as social determinants of health. Supervised deep learning was the most popular ML paradigm, while semi-supervised and weakly supervised learning were applied to expedite algorithm development and unsupervised learning to facilitate phenotype discovery. ML approaches did not uniformly outperform rule-based algorithms, but deep learning offered a marginal improvement over traditional ML for many conditions.

DISCUSSION

Despite the progress in ML-based phenotyping, most articles focused on binary phenotypes and few articles evaluated external validity or used multi-institution data. Study settings were infrequently reported and analytic code was rarely released.

CONCLUSION

Continued research in ML-based phenotyping is warranted, with emphasis on characterizing nuanced phenotypes, establishing reporting and evaluation standards, and developing methods to accommodate misclassified phenotypes due to algorithm errors in downstream applications.

The Causal Effects of Lipid Profiles on Sleep Apnea

Introduction

Observational studies have suggested that lipid profiles were associated with risk of sleep apnea (SA). However, the specific lipid types and whether this relationship has a causal effect are uncertain. This study conducted two-sample Mendelian randomization (MR) and multivariable Mendelian randomization (MVMR) to investigate the potential causal relationship between lipid profiles and risk of SA.

Materials and Methods

We used the largest genome-wide association study (GWAS) on European participants on the UK Biobank. After a rigorous single nucleotide polymorphism screening process to remove confounding effects, we performed MR and MVMR to explore the causal relationship between lipid profiles and SA risk.

Results

Both MR and MVMR showed causal effects of increased triglyceride on SA risk [MR: per 10 units, odds ratio (OR): 1.0156; 95% CI: 1.0057-1.0257; P value = 0.002; MVMR: per 10 units, OR: 1.0229; 95% CI: 1.0051-1.0411; P value = 0.011]. The sensitivity analysis including Cochran's Q test, MR-Egger intercept, and MR pleiotropy residual sum and outlier (MR-PRESSO) test indicated that our findings were robust. The causal effects of triglyceride on SA did not change after adjusting for potential confounders (obesity, age, sex, and airway obstruction).

Conclusion

Genetically increased triglyceride levels have independent causal effects on risk of sleep apnea without the confounding effects of obesity, suggesting that lowering triglyceride concentrations may help to reduce the risk of sleep apnea.